FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312450015> ?p ?o ?g. }

• W4312450015 endingPage "296" @default.
• W4312450015 startingPage "277" @default.
• W4312450015 abstract "Recent image inpainting methods have made great progress but often struggle to generate plausible image structures when dealing with large holes in complex images. This is partially due to the lack of effective network structures that can capture both the long-range dependency and high-level semantics of an image. We propose cascaded modulation GAN (CM-GAN), a new network design consisting of an encoder with Fourier convolution blocks that extract multi-scale feature representations from the input image with holes and a dual-stream decoder with a novel cascaded global-spatial modulation block at each scale level . In each decoder block, global modulation is first applied to perform coarse and semantic-aware structure synthesis, followed by spatial modulation to further adjust the feature map in a spatially adaptive fashion. In addition, we design an object-aware training scheme to prevent the network from hallucinating new objects inside holes, fulfilling the needs of object removal tasks in real-world scenarios. Extensive experiments are conducted to show that our method significantly outperforms existing methods in both quantitative and qualitative evaluation . Please refer to the project page: https://github.com/htzheng/CM-GAN-Inpainting ." @default.
• W4312450015 created "2023-01-04" @default.
• W4312450015 creator A5016267591 @default.
• W4312450015 creator A5024456511 @default.
• W4312450015 creator A5024777042 @default.
• W4312450015 creator A5042253371 @default.
• W4312450015 creator A5051116485 @default.
• W4312450015 creator A5055156362 @default.
• W4312450015 creator A5055469774 @default.
• W4312450015 creator A5067580558 @default.
• W4312450015 creator A5083898813 @default.
• W4312450015 creator A5085050428 @default.
• W4312450015 date "2022-01-01" @default.
• W4312450015 modified "2023-09-24" @default.
• W4312450015 title "Image Inpainting with Cascaded Modulation GAN and Object-Aware Training" @default.
• W4312450015 cites W1967577110 @default.
• W4312450015 cites W1993120651 @default.
• W4312450015 cites W1995672339 @default.
• W4312450015 cites W1999360130 @default.
• W4312450015 cites W2031832209 @default.
• W4312450015 cites W2040378863 @default.
• W4312450015 cites W2047957240 @default.
• W4312450015 cites W2064309976 @default.
• W4312450015 cites W2093212899 @default.
• W4312450015 cites W2100415658 @default.
• W4312450015 cites W2105038642 @default.
• W4312450015 cites W2157070558 @default.
• W4312450015 cites W2331128040 @default.
• W4312450015 cites W2557414982 @default.
• W4312450015 cites W2603777577 @default.
• W4312450015 cites W2732026016 @default.
• W4312450015 cites W2738588019 @default.
• W4312450015 cites W2798365772 @default.
• W4312450015 cites W2962770929 @default.
• W4312450015 cites W2962785568 @default.
• W4312450015 cites W2962974533 @default.
• W4312450015 cites W2963420272 @default.
• W4312450015 cites W2963814095 @default.
• W4312450015 cites W2963890275 @default.
• W4312450015 cites W2964148878 @default.
• W4312450015 cites W2981682056 @default.
• W4312450015 cites W2982695696 @default.
• W4312450015 cites W2982763192 @default.
• W4312450015 cites W2985299701 @default.
• W4312450015 cites W2998075999 @default.
• W4312450015 cites W3015643106 @default.
• W4312450015 cites W3034419329 @default.
• W4312450015 cites W3035574324 @default.
• W4312450015 cites W3043547428 @default.
• W4312450015 cites W3048675442 @default.
• W4312450015 cites W3101838243 @default.
• W4312450015 cites W3108554146 @default.
• W4312450015 cites W3109174731 @default.
• W4312450015 cites W3136958399 @default.
• W4312450015 cites W3166541011 @default.
• W4312450015 cites W3166762869 @default.
• W4312450015 cites W3170410843 @default.
• W4312450015 cites W3199003182 @default.
• W4312450015 cites W3204170321 @default.
• W4312450015 cites W4200095354 @default.
• W4312450015 doi "https://doi.org/10.1007/978-3-031-19787-1_16" @default.
• W4312450015 hasPublicationYear "2022" @default.
• W4312450015 type Work @default.
• W4312450015 citedByCount "1" @default.
• W4312450015 countsByYear W43124500152023 @default.
• W4312450015 crossrefType "book-chapter" @default.
• W4312450015 hasAuthorship W4312450015A5016267591 @default.
• W4312450015 hasAuthorship W4312450015A5024456511 @default.
• W4312450015 hasAuthorship W4312450015A5024777042 @default.
• W4312450015 hasAuthorship W4312450015A5042253371 @default.
• W4312450015 hasAuthorship W4312450015A5051116485 @default.
• W4312450015 hasAuthorship W4312450015A5055156362 @default.
• W4312450015 hasAuthorship W4312450015A5055469774 @default.
• W4312450015 hasAuthorship W4312450015A5067580558 @default.
• W4312450015 hasAuthorship W4312450015A5083898813 @default.
• W4312450015 hasAuthorship W4312450015A5085050428 @default.
• W4312450015 hasConcept C107038049 @default.
• W4312450015 hasConcept C110384440 @default.
• W4312450015 hasConcept C111919701 @default.
• W4312450015 hasConcept C115961682 @default.
• W4312450015 hasConcept C11727466 @default.
• W4312450015 hasConcept C118505674 @default.
• W4312450015 hasConcept C123079801 @default.
• W4312450015 hasConcept C138885662 @default.
• W4312450015 hasConcept C153180895 @default.
• W4312450015 hasConcept C154945302 @default.
• W4312450015 hasConcept C2524010 @default.
• W4312450015 hasConcept C2776401178 @default.
• W4312450015 hasConcept C2777210771 @default.
• W4312450015 hasConcept C2781238097 @default.
• W4312450015 hasConcept C2911011789 @default.
• W4312450015 hasConcept C31972630 @default.
• W4312450015 hasConcept C33923547 @default.
• W4312450015 hasConcept C41008148 @default.
• W4312450015 hasConcept C41895202 @default.
• W4312450015 hasConcept C45347329 @default.
• W4312450015 hasConcept C50644808 @default.
• W4312450015 hasConceptScore W4312450015C107038049 @default.

• next